Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Why Learn What Physics Already Knows? Realizing Agile mmWave-based Human Pose Estimation via Physics-Guided Preprocessing

About

We revisit millimeter-wave (mmWave) human pose estimation (HPE) from a signal preprocessing perspective. A single mmWave frame provides structured dimensions that map directly to human geometry and motion: range, angle, and Doppler, offering pose-aligned cues that are not explicitly present in RGB images. However, recent mmWave-based HPE systems require more parameters and compute resources yet yield lower estimation accuracy than vision baselines. We attribute this to preprocessing modules: most systems rely on data-driven modules to estimate phenomena that are already well-defined by mmWave sensing physics, whereas human pose could be captured more efficiently with explicit physical priors. To this end, we introduce processing modules that explicitly model mmWave's inter-dimensional correlations and human kinematics. Our design (1) couples range and angle to preserve spatial human structure, (2) leverages Doppler to retain human motion continuity, and (3) applies multi-scale fusion aligned with the human body. A lightweight MLP is involved as the regressor. In experiments, this framework reduces the number of parameters by 55.7-88.9% on the HPE task relative to existing mmWave baselines while maintaining competitive accuracy. Meanwhile, its lightweight nature enables real-time Raspberry Pi deployment. Code and deployment artifacts will be released upon acceptance.

Shuntian Zheng, Jiaqi Li, Minzhe Ni, Xiaoman Lu, Yu Guan• 2026

Related benchmarks

TaskDatasetResultRank
Human Pose EstimationHuPR (test)
MAJPE64.16
19
Human Pose EstimationXRF55
MAJPE73.09
15
Showing 2 of 2 rows

Other info

Follow for update